© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-65K
    7. 2378
    Prev
    Next
    INDEX
    Explanations

    convolutional hallucinations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     a
    0.82
    c
    0.75
    ī
    0.65
    væ
    0.63
    し
    0.60
     stethoscope
    0.59
    一
    0.59
    bott
    0.58
    re
    0.57
    cV
    0.57
    POSITIVE LOGITS
    و
    0.79
    ו
    0.75
     dominante
    0.68
    ﺩ
    0.67
     delito
    0.64
    9
    0.63
     doctrina
    0.62
     Česk
    0.61
     пур
    0.61
    ederal
    0.60
    Activations Density 0.390%

    No Known Activations